AI is rapidly spreading throughout civilization, where it strongly promises to do everything, to change us and our everyday lives. This technology grows more sophisticated and capable of absolutely transforming many industries as health, transportation, retail, media, etc.
So continuing the series of articles on Munich AI Summit 2019 talks, today we’re going to explore another interesting topic. Our next speaker Tigran Sukiasyan focused on machine learning use cases in financial services. He touched upon traditional credit risk management approaches contrasting them with the new machine learning-based techniques. Furthermore, he discussed different approaches for estimating the probability of credit default and explained it by presenting in detail the credit risk management engine developed by Develandoo AI Innovation Lab called Protogen AI.
Tigran Sukiasyan has over 5 years of extensive experience in machine learning engineering working for financial, government and international institutions. He consults firms on digital strategy & transformation and develops predictive algorithms for data-driven policymaking.
‘’We all know that data science can be interpreted as a mixture of some fields. There is the domain part, the math and statistics part, and of course, there’s the programming part. And what we are actually trying to do at Protegen AI is to bring together the expertise of all of these fields and build innovative products for the financial sector,’’ said Sukiasyan.
So in terms of real examples, Tigran spoke about ZestFinance which applies big data analysis to credit card data.
‘’They do scoring and got the investment of 272 mln dollars in 2016. Actually, with their models, they reduced the default rate in credit portfolio a lot, which of course results in higher profits for the bank. So they actually had a very successful case in China working with the search engine Baidu. This is just one example that may summarize what’s going on in this field in terms of credit scoring but on top of this, central banks may also use this kind of more innovative techniques in order to develop ML-based algorithms for credit scoring. And why I’m saying this because they possess the data of all the system, for example, the credit bureau data. They have even bigger data than commercial banks may possess separately. They may do real-time modern monitoring of credit quality with some financial stability implications, and they may provide already trained algorithms based on these systemic data to new banks. It may be an important factor. So a new bank without any knowledge about the economy may possess the already trained algorithm and may freely provide loans,’’ explained our speaker.
Further, he talked about Protogen AI exploring the topic on the example of this financial credit risk scoring system built on state-of-the-art machine learning techniques. The system aims at predicting the probability of customers defaulting with high accuracy and speed as well as providing post prediction analysis tools for the interpretation of the system’s workings. With Protogen AI customers can obtain credit risk scores with higher accuracy and in a matter of seconds, compared to current state-of-the-art approaches. It also treats the model as something other than a black box, since Protogen provides model interpretation tool that helps customers understand its workings on the backend.
This was just a small piece from our speaker’s talk. If you want to learn more about the topic, you can visit our youtube channel where you’ll find the videos of all the Munich AI Summit talks.
Additionally, you can find more information about the above-mentioned product Protogen AI here.
We are thankful to all our sponsors (Fujitsu, Women in AI, Liquid Newsroom, Scylla and Urgestain, Wayra Germany), participants and the speakers for attending our Munich-AI Summit 2019, the one and only free event in Munich area related to AI.
As we have already informed, we have many big plans related to this initiative. We’re officially launching AI Summit in different countries. In 2020 our destination is Yerevan, the beautiful capital of Armenia. So stay tuned to our blog where we’ll share further details of our upcoming event.
Develandoo has also incubated three in-house startups which are leading the markets in their areas of expertise:
- Scylla – World’s leading gun detection system
- Cibola – World’s first in-store analytics system
- Protogen – Generic Tabular Data platform
For more information, please visit – https://develandoo.com